web-edit 0.1a0
- ID
- 34802
- Status
- summarized
- Published
- 12 Oct 2026, 11:54 PM
- Fetched
- 13 Oct 2026, 9:44 PM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Oct/12/web-edit/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 5.0
- Created
- 13 Oct 2026, 9:44 PM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
Simon Willison released web-edit 0.1a0, a small Python web app that gives a browser UI for browsing and editing files in a folder, which he built with Codex and 'GPT-6 Astra Extra High' after wanting to edit a credentials file from his phone via Codex Remote without routing those credentials through the LLM. It uses CodeMirror 6 for editing — he says he considered Monaco but it still lacks a good mobile experience — and is designed to be run over Tailscale so an agent can start it and he can reach it directly from his phone.
Why it matters
The useful idea is the split it enables: let the agent run commands on your machine, but keep secrets out of the model's context by editing those files yourself through a local web UI on your tailnet. If you do remote agent-assisted coding, that is a concrete alternative to pasting a .env or credentials file into a chat. Note it is a 0.1a0 alpha whose security model is essentially 'Tailscale-only' — do not expose it on a public interface.
Discussion angle
How do you let an agent work in a repo without handing it your secrets? Worth comparing approaches live: Tailscale-only local editor UIs, secret injection at runtime, and whether anyone has a workflow that keeps credentials entirely outside model context.